refactor(news): remove retired research workflow
This commit is contained in:
1 parent
f3894c3728
commit
d79a10c2e6
69 files changed
+460
-6713
No files matched your search
@@ -1,187 +1,22 @@
|
||||
"""Risk evidence, identity and model boundaries use synthetic inputs only."""
|
||||
import asyncio
|
||||
from datetime import UTC, datetime
|
||||
import pytest
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def risk(trading):
|
||||
from alphapulse.news_risk import service
|
||||
from alphapulse.news_research import model as service
|
||||
return service
|
||||
|
||||
|
||||
def label(risk, **values):
|
||||
return risk.Label(id=1, title='交易所安全事件', summary='媒体报道交易所安全事件', category='security',
|
||||
entities=['Exchange'], stars=5, direction='bearish', verification='unverified', confidence='low',
|
||||
reasoning='重大资金安全风险', uncertainty='规模尚待核实', evidence='安全事件', event_id=None, **values)
|
||||
|
||||
|
||||
def test_risk_start_is_beijing_midnight(risk):
|
||||
assert risk.START == datetime(2026, 10, 25, 16, tzinfo=UTC)
|
||||
|
||||
|
||||
def test_extreme_unverified_event_preserves_uncertainty(risk):
|
||||
item = label(risk)
|
||||
risk.validate_labels(risk.Labels(items=[item]), {1: {'title': '安全事件'}}, set())
|
||||
assert item.stars == 5 and item.verification == 'unverified'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('evidence', ['安全事件', ' 安全事件\n', '“安全事件”', '「安全事件」', '‘安全事件’', '"安全事件"', "'安全事件'"])
|
||||
def test_evidence_presentation_quotes_preserve_literal_source(risk, evidence):
|
||||
item = label(risk).model_copy(update={'evidence': evidence})
|
||||
risk.validate_labels(risk.Labels(items=[item]), {1: {'content': '媒体报道安全事件,规模待核实。'}}, set())
|
||||
assert item.evidence == '安全事件'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('evidence', ['“资产已被盗”', '安全…事件', 'security incident', ' ', '“”', '标题\n正文'])
|
||||
def test_evidence_must_be_nonempty_and_from_one_source_field(risk, evidence):
|
||||
item = label(risk).model_copy(update={'evidence': evidence})
|
||||
with pytest.raises(ValueError, match='模型证据并非输入原文引用'):
|
||||
risk.validate_labels(risk.Labels(items=[item]), {1: {'title': '标题', 'summary': '正文', 'content': '安全事件'}}, set())
|
||||
|
||||
|
||||
def test_evidence_retains_quotes_present_in_source(risk):
|
||||
item = label(risk).model_copy(update={'evidence': '“安全事件”'})
|
||||
risk.validate_labels(risk.Labels(items=[item]), {1: {'content': '媒体称这是“安全事件”。'}}, set())
|
||||
assert item.evidence == '“安全事件”'
|
||||
|
||||
|
||||
def mock_enable(risk, monkeypatch, valid=True, verification='reported', direction='neutral'):
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock, MagicMock
|
||||
from alphapulse.core import db
|
||||
gate = MagicMock()
|
||||
gate.__aenter__ = AsyncMock(return_value=gate)
|
||||
gate.__aexit__ = AsyncMock(return_value=None)
|
||||
gate.scalar = AsyncMock(return_value=True)
|
||||
gate.execute = AsyncMock()
|
||||
gate.commit = AsyncMock()
|
||||
monkeypatch.setattr(db, "engine", SimpleNamespace(connect=lambda: gate))
|
||||
from alphapulse.news_risk import pipeline, briefing
|
||||
from alphapulse.api import risk as api
|
||||
provider = SimpleNamespace(model='news-only', max_tokens=1000, context_window=200000)
|
||||
session = SimpleNamespace(get=AsyncMock(return_value=None), merge=AsyncMock(), commit=AsyncMock())
|
||||
monkeypatch.setattr(pipeline, 'configuration', AsyncMock(return_value=(provider, 'rules', {}, 'fingerprint')))
|
||||
async def complete(provider, system, payload, schema):
|
||||
if schema is pipeline.Grouping:
|
||||
return pipeline.Grouping( reason='财经维护通知', packages=[pipeline.Match(event=dict(event_id=None,group_key='maintenance',title='维护',fact='维护',reason='维护通知'),package_id=None,
|
||||
group_key='maintenance', title='维护', category='company', entities=['示例公司'], fact='维护',
|
||||
evidence=payload['article']['summary'] if valid else '捏造损失', urgent=False, tags=['维护'], content_kind='statement')]), {}
|
||||
if schema is risk.Outlook:
|
||||
return risk.Outlook(windows=[risk.Scenario(hours=h, direction='unknown', summary='不足', conditions='不足',
|
||||
counter_factors='不足', uncertainty='不足', event_ids=[]) for h in (24, 48, 168)]), {}
|
||||
article = payload['articles'][0]
|
||||
from alphapulse.news_risk.event_research import EventResult
|
||||
result = EventResult(**{**label(risk).model_dump(exclude={'event_id', 'same_event_as', 'evidence', 'stars'}), 'verification': verification,
|
||||
'direction': direction}, timeline_points=[dict(package_id=1,package_revision=1,occurred_at=None, time_precision='unknown', time_text='Unknown', reported_at=None, description='Synthetic', verification='insufficient', evidence_refs=[{'article_id':1,'quote':article['summary']}])], facts='维护', timeline='维护',
|
||||
asset_impacts='未知', risk_stars=0, importance_stars=3, opinions='待观察', counter_evidence='不足', watchpoints='恢复', claims=[pipeline.Claim(statement='维护', verdict='insufficient', evidence_refs=[])], excluded_article_ids=[],
|
||||
evidence_refs=[pipeline.Evidence(article_id=1, quote=article['summary'])])
|
||||
return result, {}
|
||||
async def high(provider, system, payload, schema):
|
||||
if schema is briefing.Ranked:
|
||||
return briefing.Ranked(reading=[briefing.Reading(kind=p.get('kind','event'),id=p['id'], revision=p['revision'], priority=50, reason='重要') for p in payload['packages']], notes='虚构测试'), {}
|
||||
trend = briefing.Trend(summary='未知', conditions='不足', counter_evidence='不足', watchpoints='后续')
|
||||
return briefing.Synthesis(summary='不足', market='未知', short_term=trend, medium_term=trend, references=[]), {}
|
||||
monkeypatch.setattr(briefing, 'complete', high)
|
||||
monkeypatch.setattr(api, 'complete', complete)
|
||||
monkeypatch.setattr(pipeline, 'complete', complete)
|
||||
return session
|
||||
|
||||
|
||||
def enable_response(session):
|
||||
from fastapi import FastAPI
|
||||
import httpx
|
||||
from alphapulse.api import risk as api
|
||||
app = FastAPI()
|
||||
app.include_router(api.router)
|
||||
app.dependency_overrides[api.require_admin] = lambda: None
|
||||
app.dependency_overrides[api.get_session] = lambda: session
|
||||
async def check():
|
||||
async with httpx.AsyncClient(transport=httpx.ASGITransport(app), base_url='http://test') as client:
|
||||
return await client.post('/api/risk/enable', json={'provider_id': 1, 'model': 'news-only'})
|
||||
return asyncio.run(check())
|
||||
|
||||
|
||||
@pytest.mark.parametrize('valid', [True, False])
|
||||
def test_enable_validates_evidence_before_saving_settings(risk, monkeypatch, valid):
|
||||
session = mock_enable(risk, monkeypatch, valid)
|
||||
response = enable_response(session)
|
||||
assert response.status_code == (200 if valid else 502), response.text
|
||||
if valid:
|
||||
saved = session.merge.call_args.args[0]
|
||||
assert saved.enabled and saved.start_at is not None
|
||||
assert session.commit.await_count == 4
|
||||
else:
|
||||
assert '原文引用' in response.text
|
||||
session.merge.assert_not_awaited()
|
||||
|
||||
|
||||
@pytest.mark.parametrize('verification,direction,status', [
|
||||
('insufficient', 'unknown', 200), ('insufficient', 'neutral', 502), ('insufficient', 'bullish', 502),
|
||||
('insufficient', 'bearish', 502), ('insufficient', 'mixed', 502), ('reported', 'neutral', 200),
|
||||
])
|
||||
def test_enable_requires_consistent_uncertainty_without_changing_model_output(risk, monkeypatch, verification, direction, status):
|
||||
session = mock_enable(risk, monkeypatch, verification=verification, direction=direction)
|
||||
response = enable_response(session)
|
||||
assert response.status_code == status, response.text
|
||||
if status == 200:
|
||||
session.merge.assert_awaited_once()
|
||||
else:
|
||||
assert '无法判断方向' in response.text
|
||||
session.merge.assert_not_awaited()
|
||||
|
||||
|
||||
def test_uncertainty_contract_reaches_the_model_with_tool_schema(risk, monkeypatch):
|
||||
from types import SimpleNamespace
|
||||
item = label(risk).model_copy(update={'verification': 'insufficient', 'direction': 'unknown'})
|
||||
|
||||
async def stream(provider, system, messages, tools, effort):
|
||||
assert 'verification="insufficient", direction="unknown"' in system
|
||||
fields = tools[0].parameters['$defs']['Label']['properties']
|
||||
assert 'insufficient' in fields['direction']['description']
|
||||
assert 'unknown' in fields['verification']['description']
|
||||
yield risk.llm.Completion(tool_calls=[{'name': 'submit', 'arguments': {'items': [item.model_dump()]}}])
|
||||
|
||||
monkeypatch.setattr(risk.llm, 'stream', stream)
|
||||
payload = {'news': [{'id': 1, 'title': '安全事件'}], 'candidates': []}
|
||||
provider = SimpleNamespace(max_tokens=256, context_window=200000, reasoning_effort=None)
|
||||
result, _ = asyncio.run(risk.complete(provider, risk.SYSTEM, payload, risk.Labels))
|
||||
risk.validate_labels(result, {1: payload['news'][0]}, set())
|
||||
assert result.items[0].direction == 'unknown'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('kind', ['missing', 'duplicate', 'unknown', 'evidence', 'candidate', 'insufficient'])
|
||||
def test_invalid_results_are_rejected(risk, kind):
|
||||
item = label(risk)
|
||||
if kind == 'missing': items = []
|
||||
elif kind == 'duplicate': items = [item, item]
|
||||
else:
|
||||
if kind == 'unknown': item.id = 2
|
||||
if kind == 'evidence': item.evidence = '捏造的跌幅6%'
|
||||
if kind == 'candidate': item.event_id = 999
|
||||
if kind == 'insufficient': item.verification = 'insufficient'
|
||||
items = [item]
|
||||
with pytest.raises(ValueError):
|
||||
risk.validate_labels(risk.Labels(items=items), {1: {'title': '安全事件'}}, set())
|
||||
|
||||
|
||||
def test_same_batch_grouping_must_not_cycle(risk):
|
||||
first = label(risk)
|
||||
second = label(risk).model_copy(update={'id': 2, 'same_event_as': 1})
|
||||
inputs = {1: {'title': '安全事件'}, 2: {'title': '安全事件'}}
|
||||
risk.validate_labels(risk.Labels(items=[second, first]), inputs, set())
|
||||
first.same_event_as = 2
|
||||
with pytest.raises(ValueError):
|
||||
risk.validate_labels(risk.Labels(items=[first, second]), inputs, set())
|
||||
|
||||
|
||||
def test_truncated_completion_is_not_a_safe_label(risk, monkeypatch):
|
||||
from alphapulse.news_research.contracts import IndexResult
|
||||
from types import SimpleNamespace
|
||||
async def stream(*args):
|
||||
yield risk.llm.Completion(truncated=True, usage={'output_tokens': 100})
|
||||
monkeypatch.setattr(risk.llm, 'stream', stream)
|
||||
with pytest.raises(risk.OutputTruncated, match='截断') as exc:
|
||||
asyncio.run(risk.complete(SimpleNamespace(max_tokens=100, context_window=10000, reasoning_effort=None), '', {}, risk.Labels))
|
||||
asyncio.run(risk.complete(SimpleNamespace(max_tokens=100, context_window=10000, reasoning_effort=None), '', {}, IndexResult))
|
||||
assert exc.value.usage == {'output_tokens': 100}
|
||||
|
||||
|
||||
@@ -196,128 +31,8 @@ def test_model_override_never_changes_shared_provider(risk):
|
||||
assert session.detached == 'original' and result.model == 'LUNA'
|
||||
|
||||
|
||||
def test_debounce_is_bounded_and_urgent_bypasses_wait(risk):
|
||||
from datetime import timedelta
|
||||
from types import SimpleNamespace
|
||||
from alphapulse.news_risk.worker import schedule
|
||||
now = datetime.now(UTC)
|
||||
event = SimpleNamespace(revision=1, result={'summary': '原总结'}, dirty_since=now-timedelta(seconds=170))
|
||||
schedule(event, now, False)
|
||||
assert event.due_at == now+timedelta(seconds=10)
|
||||
assert event.revision == 2
|
||||
schedule(event, now, True)
|
||||
assert event.due_at == now
|
||||
|
||||
|
||||
def test_long_sources_are_split_without_losing_text(risk, monkeypatch):
|
||||
from types import SimpleNamespace
|
||||
from alphapulse.news_risk import pipeline
|
||||
provider = SimpleNamespace(max_tokens=100, context_window=10000)
|
||||
article = {'id': 1, 'title': '安全事件', 'summary': '', 'content': '安'*16000}
|
||||
seen = []
|
||||
async def complete(provider, system, payload, schema):
|
||||
if payload['task'] == 'extract':
|
||||
seen.append(payload['content'])
|
||||
return schema(facts='事实', evidence_refs=[pipeline.Evidence(article_id=1, quote=payload['content'][:1])]), {}
|
||||
return pipeline.EventResult(**label(risk).model_dump(exclude={'event_id', 'same_event_as', 'evidence', 'stars'}), timeline_points=[dict(package_id=1,package_revision=1,occurred_at=None, time_precision='unknown', time_text='Unknown', reported_at=None, description='Synthetic', verification='insufficient', evidence_refs=[{'article_id':1,'quote':'安全事件'}])], facts='事实', timeline='时间', asset_impacts='资产',
|
||||
risk_stars=5, importance_stars=5, opinions='待观察', counter_evidence='不足', watchpoints='恢复', claims=[pipeline.Claim(statement='事件', verdict='insufficient', evidence_refs=[])], related_packages=[], excluded_article_ids=[], evidence_refs=[pipeline.Evidence(article_id=1, quote='安全事件')]), {}
|
||||
monkeypatch.setattr(pipeline, 'complete', complete)
|
||||
result, _ = asyncio.run(pipeline.summarize_articles(provider, 'rules', [article], {'id': 1, 'fact': 'Synthetic event'}))
|
||||
assert ''.join(seen) == article['title']+'\n\n'+article['content']
|
||||
assert result.risk_stars == 5
|
||||
|
||||
|
||||
def test_context_budget_includes_unicode_and_tool_schema(risk):
|
||||
from alphapulse.news_research.contracts import IndexResult
|
||||
from types import SimpleNamespace
|
||||
provider = SimpleNamespace(max_tokens=256, context_window=4096)
|
||||
assert not risk.fits_context(provider, risk.SYSTEM, {'content': '风'*1000}, risk.Labels)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('endpoint', ['overview', 'events'])
|
||||
@pytest.mark.parametrize('hours,status', [(None, 200), ('24', 200), ('48', 200), ('168', 200), ('25', 422), ('0', 422), ('abc', 422)])
|
||||
def test_window_query_parameters_over_http(risk, monkeypatch, endpoint, hours, status):
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock
|
||||
from fastapi import FastAPI
|
||||
import httpx
|
||||
from alphapulse.api import risk as api
|
||||
|
||||
session = SimpleNamespace(get=AsyncMock(return_value=None), execute=AsyncMock(return_value=SimpleNamespace(all=lambda: [])),
|
||||
scalar=AsyncMock(return_value=None), scalars=AsyncMock(return_value=SimpleNamespace(all=lambda: [])))
|
||||
app = FastAPI()
|
||||
app.include_router(api.router)
|
||||
app.dependency_overrides[api.require_admin] = lambda: None
|
||||
app.dependency_overrides[api.get_session] = lambda: session
|
||||
monkeypatch.setattr(api, 'coverage', AsyncMock(return_value={'pending': 0}))
|
||||
monkeypatch.setattr(api.redis, 'get', AsyncMock(return_value=None))
|
||||
|
||||
async def check():
|
||||
async with httpx.AsyncClient(transport=httpx.ASGITransport(app), base_url='http://test') as client:
|
||||
response = await client.get('/api/risk/'+endpoint, params={} if hours is None else {'hours': hours})
|
||||
assert response.status_code == status, response.text
|
||||
if status == 200:
|
||||
assert response.json()['code'] == 0
|
||||
asyncio.run(check())
|
||||
|
||||
|
||||
def test_fresh_settings_can_be_saved_without_editing_any_fields(risk):
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock
|
||||
from fastapi import FastAPI
|
||||
import httpx
|
||||
from alphapulse.api import risk as api
|
||||
session = SimpleNamespace(get=AsyncMock(return_value=None), scalar=AsyncMock(return_value=None),
|
||||
merge=AsyncMock(), commit=AsyncMock())
|
||||
app = FastAPI()
|
||||
app.include_router(api.router)
|
||||
app.dependency_overrides[api.require_admin] = lambda: None
|
||||
app.dependency_overrides[api.get_session] = lambda: session
|
||||
async def check():
|
||||
async with httpx.AsyncClient(transport=httpx.ASGITransport(app), base_url='http://test') as client:
|
||||
response = await client.get('/api/risk/settings')
|
||||
assert response.status_code == 200
|
||||
value = response.json()['data']
|
||||
assert value['second_model'] == value['third_model'] == ''
|
||||
response = await client.put('/api/risk/settings', json=value)
|
||||
assert response.status_code == 200, response.text
|
||||
asyncio.run(check())
|
||||
saved = session.merge.call_args.args[0]
|
||||
assert saved.enabled is False and saved.third_model == ''
|
||||
session.commit.assert_awaited_once()
|
||||
|
||||
|
||||
@pytest.mark.parametrize('state,published,reason', [('done', 3, '成功结果'), ('pending', 2, '排队'), ('processing', 2, '正在处理')])
|
||||
def test_old_failed_analysis_cannot_requeue_a_completed_or_running_revision(risk, state, published, reason):
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock
|
||||
from fastapi import HTTPException
|
||||
from alphapulse.api import risk as api
|
||||
event = SimpleNamespace(revision=3, published_revision=published, state=state)
|
||||
row = SimpleNamespace(state='failed', event_id=1, revision=3)
|
||||
session = SimpleNamespace(get=AsyncMock(side_effect=[row, event]), commit=AsyncMock())
|
||||
with pytest.raises(HTTPException) as exc:
|
||||
asyncio.run(api.retry(7, session, stage='events'))
|
||||
assert exc.value.status_code == 409
|
||||
assert event.state == state
|
||||
session.commit.assert_not_awaited()
|
||||
|
||||
|
||||
def test_completed_version_recovers_a_previously_stuck_pending_package(risk, monkeypatch):
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock
|
||||
from alphapulse.news_risk import worker
|
||||
event = SimpleNamespace(review_config=None, result=None, id=1, revision=3, published_revision=3, state='pending', error='Old failure',
|
||||
dirty_since=datetime.now(UTC), title='Statement', fact='Statement', category='politics', tags=['Statement'], content_kind='statement')
|
||||
session = AsyncMock()
|
||||
session.__aenter__.return_value = session
|
||||
session.get.return_value = SimpleNamespace(enabled=True)
|
||||
session.scalar.side_effect = [event, SimpleNamespace(state='done')]
|
||||
session.scalars.return_value = SimpleNamespace(all=lambda: [SimpleNamespace(id=1, news_id=10, content_hash='current', input={'title': 'Statement'})])
|
||||
monkeypatch.setattr(worker, 'SessionLocal', lambda: session)
|
||||
monkeypatch.setattr(worker, 'configuration', AsyncMock(return_value=(SimpleNamespace(model='medium'), 'rules', {}, 'key')))
|
||||
analyze = AsyncMock()
|
||||
monkeypatch.setattr(worker, 'summarize_articles', analyze)
|
||||
asyncio.run(worker.summarize())
|
||||
assert event.state == 'done' and event.error is None and event.dirty_since is None
|
||||
session.commit.assert_awaited_once()
|
||||
analyze.assert_not_awaited()
|
||||
provider = SimpleNamespace(max_tokens=256, context_window=3500)
|
||||
assert not risk.fits_context(provider, '只使用原文证据', {'content': '风'*1000}, IndexResult)
|
||||
Reference in new issue
Block a user